Automating Galaxy Image Classification in Galaxy Zoo: A Comparative Study of Deep Learning Models

Soon Piin Chiew; Chung Fan Liau; Ali Farzamnia

doi:10.1007/978-981-97-2027-9_18

Automating Galaxy Image Classification in Galaxy Zoo: A Comparative Study of Deep Learning Models

Soon Piin Chiew, Chung Fan Liau, Ali Farzamnia

University Malaysia Sabah

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

This study compares the effectiveness of Artificial Neural Networks (ANNs) and Logistic Regression in classifying galaxy images from Galaxy Zoo 1. We propose Convolutional Neural Network (CNN) and Autoencoder models as potential solutions to mitigate the burden of manual classification. Both models are analyzed, and results reveal that ANN surpasses Transferred Learning Logistic Regression in terms of accuracy and runtime. Further investigation highlights the impact of activation functions, neuron count, hidden layers, and algorithm ensembling on ANN's classification performance. Additionally, we explore training time complexity reduction through learning rate, optimization algorithms, and batch size. The findings provide valuable insights for galaxy image classification tasks.

Original language	English
Title of host publication	Proceedings of the 13th National Technical Seminar on Unmanned System Technology 2023—Volume 2
Subtitle of host publication	NUSYS’23
Editors	Zainah Md. Zain, Zool Hilmi Ismail, Huiping Li, Xianbo Xiang, Rama Rao Karri
Publisher	Springer Singapore
Pages	219-235
Number of pages	17
Volume	1184
Edition	1st
ISBN (Electronic)	9789819720279
ISBN (Print)	9789819720262, 9789819720293
DOIs	https://doi.org/10.1007/978-981-97-2027-9_18
Publication status	Published - 17 Sept 2024
Event	13th National Technical Symposium on Unmanned System Technology - Penang, Malaysia Duration: 2 Oct 2023 → 3 Oct 2023 Conference number: 13

Publication series

Name	Lecture Notes in Electrical Engineering
Publisher	Springer
Volume	1184 LNEE
ISSN (Print)	1876-1100
ISSN (Electronic)	1876-1119

Conference

Conference	13th National Technical Symposium on Unmanned System Technology
Abbreviated title	NUSYS 2023
Country/Territory	Malaysia
City	Penang
Period	2/10/23 → 3/10/23

Access to Document

10.1007/978-981-97-2027-9_18Licence: Unspecified

Cite this

Chiew, S. P., Liau, C. F., & Farzamnia, A. (2024). Automating Galaxy Image Classification in Galaxy Zoo: A Comparative Study of Deep Learning Models. In Z. Md. Zain, Z. H. Ismail, H. Li, X. Xiang, & R. R. Karri (Eds.), Proceedings of the 13th National Technical Seminar on Unmanned System Technology 2023—Volume 2 : NUSYS’23 (1st ed., Vol. 1184, pp. 219-235). (Lecture Notes in Electrical Engineering; Vol. 1184 LNEE). Springer Singapore. https://doi.org/10.1007/978-981-97-2027-9_18

Chiew, Soon Piin ; Liau, Chung Fan ; Farzamnia, Ali. / Automating Galaxy Image Classification in Galaxy Zoo : A Comparative Study of Deep Learning Models. Proceedings of the 13th National Technical Seminar on Unmanned System Technology 2023—Volume 2 : NUSYS’23. editor / Zainah Md. Zain ; Zool Hilmi Ismail ; Huiping Li ; Xianbo Xiang ; Rama Rao Karri. Vol. 1184 1st. ed. Springer Singapore, 2024. pp. 219-235 (Lecture Notes in Electrical Engineering).

@inproceedings{0f7ac34fd6df46ada19c655dac9ed8ee,

title = "Automating Galaxy Image Classification in Galaxy Zoo: A Comparative Study of Deep Learning Models",

abstract = "This study compares the effectiveness of Artificial Neural Networks (ANNs) and Logistic Regression in classifying galaxy images from Galaxy Zoo 1. We propose Convolutional Neural Network (CNN) and Autoencoder models as potential solutions to mitigate the burden of manual classification. Both models are analyzed, and results reveal that ANN surpasses Transferred Learning Logistic Regression in terms of accuracy and runtime. Further investigation highlights the impact of activation functions, neuron count, hidden layers, and algorithm ensembling on ANN's classification performance. Additionally, we explore training time complexity reduction through learning rate, optimization algorithms, and batch size. The findings provide valuable insights for galaxy image classification tasks.",

keywords = "Autoencoders, Image classification, Logistic Regression, Machine learning, Transferred learning",

author = "Chiew, \{Soon Piin\} and Liau, \{Chung Fan\} and Ali Farzamnia",

note = "Publisher Copyright: {\textcopyright} The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.; 13th National Technical Symposium on Unmanned System Technology, NUSYS 2023 ; Conference date: 02-10-2023 Through 03-10-2023",

year = "2024",

month = sep,

day = "17",

doi = "10.1007/978-981-97-2027-9\_18",

language = "English",

isbn = "9789819720262",

volume = "1184",

series = "Lecture Notes in Electrical Engineering",

publisher = "Springer Singapore",

pages = "219--235",

editor = "\{Md. Zain\}, Zainah and Ismail, \{Zool Hilmi\} and Huiping Li and Xianbo Xiang and Karri, \{Rama Rao\}",

booktitle = "Proceedings of the 13th National Technical Seminar on Unmanned System Technology 2023—Volume 2",

address = "Singapore",

edition = "1st",

}

Chiew, SP, Liau, CF & Farzamnia, A 2024, Automating Galaxy Image Classification in Galaxy Zoo: A Comparative Study of Deep Learning Models. in Z Md. Zain, ZH Ismail, H Li, X Xiang & RR Karri (eds), Proceedings of the 13th National Technical Seminar on Unmanned System Technology 2023—Volume 2 : NUSYS’23. 1st edn, vol. 1184, Lecture Notes in Electrical Engineering, vol. 1184 LNEE, Springer Singapore, pp. 219-235, 13th National Technical Symposium on Unmanned System Technology, Penang, Malaysia, 2/10/23. https://doi.org/10.1007/978-981-97-2027-9_18

Automating Galaxy Image Classification in Galaxy Zoo: A Comparative Study of Deep Learning Models. / Chiew, Soon Piin; Liau, Chung Fan; Farzamnia, Ali.
Proceedings of the 13th National Technical Seminar on Unmanned System Technology 2023—Volume 2 : NUSYS’23. ed. / Zainah Md. Zain; Zool Hilmi Ismail; Huiping Li; Xianbo Xiang; Rama Rao Karri. Vol. 1184 1st. ed. Springer Singapore, 2024. p. 219-235 (Lecture Notes in Electrical Engineering; Vol. 1184 LNEE).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Automating Galaxy Image Classification in Galaxy Zoo

T2 - 13th National Technical Symposium on Unmanned System Technology

AU - Chiew, Soon Piin

AU - Liau, Chung Fan

AU - Farzamnia, Ali

N1 - Conference code: 13

PY - 2024/9/17

Y1 - 2024/9/17

N2 - This study compares the effectiveness of Artificial Neural Networks (ANNs) and Logistic Regression in classifying galaxy images from Galaxy Zoo 1. We propose Convolutional Neural Network (CNN) and Autoencoder models as potential solutions to mitigate the burden of manual classification. Both models are analyzed, and results reveal that ANN surpasses Transferred Learning Logistic Regression in terms of accuracy and runtime. Further investigation highlights the impact of activation functions, neuron count, hidden layers, and algorithm ensembling on ANN's classification performance. Additionally, we explore training time complexity reduction through learning rate, optimization algorithms, and batch size. The findings provide valuable insights for galaxy image classification tasks.

AB - This study compares the effectiveness of Artificial Neural Networks (ANNs) and Logistic Regression in classifying galaxy images from Galaxy Zoo 1. We propose Convolutional Neural Network (CNN) and Autoencoder models as potential solutions to mitigate the burden of manual classification. Both models are analyzed, and results reveal that ANN surpasses Transferred Learning Logistic Regression in terms of accuracy and runtime. Further investigation highlights the impact of activation functions, neuron count, hidden layers, and algorithm ensembling on ANN's classification performance. Additionally, we explore training time complexity reduction through learning rate, optimization algorithms, and batch size. The findings provide valuable insights for galaxy image classification tasks.

KW - Autoencoders

KW - Image classification

KW - Logistic Regression

KW - Machine learning

KW - Transferred learning

UR - https://www.scopus.com/pages/publications/85205132957

UR - https://doi.org/10.1007/978-981-97-2027-9

U2 - 10.1007/978-981-97-2027-9_18

DO - 10.1007/978-981-97-2027-9_18

M3 - Conference contribution

AN - SCOPUS:85205132957

SN - 9789819720262

SN - 9789819720293

VL - 1184

T3 - Lecture Notes in Electrical Engineering

SP - 219

EP - 235

BT - Proceedings of the 13th National Technical Seminar on Unmanned System Technology 2023—Volume 2

A2 - Md. Zain, Zainah

A2 - Ismail, Zool Hilmi

A2 - Li, Huiping

A2 - Xiang, Xianbo

A2 - Karri, Rama Rao

PB - Springer Singapore

Y2 - 2 October 2023 through 3 October 2023

ER -

Chiew SP, Liau CF, Farzamnia A. Automating Galaxy Image Classification in Galaxy Zoo: A Comparative Study of Deep Learning Models. In Md. Zain Z, Ismail ZH, Li H, Xiang X, Karri RR, editors, Proceedings of the 13th National Technical Seminar on Unmanned System Technology 2023—Volume 2 : NUSYS’23. 1st ed. Vol. 1184. Springer Singapore. 2024. p. 219-235. (Lecture Notes in Electrical Engineering). Epub 2024 Sept 16. doi: 10.1007/978-981-97-2027-9_18

Automating Galaxy Image Classification in Galaxy Zoo: A Comparative Study of Deep Learning Models

Abstract

Publication series

Conference

Access to Document

Other files and links

Fingerprint

Cite this